Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1649 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0006

Data Index: 425015 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0351. Min Act: -0.0005

Data Index: 470189 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0345. Min Act: -0.0006

Data Index: 986565 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1301723 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1085357 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0304. Min Act: -0.0006

Data Index: 769996 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0294. Min Act: -0.0006

Data Index: 783123 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0286. Min Act: -0.0006

Data Index: 372463 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0274. Min Act: -0.0006

Data Index: 829805 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0296. Min Act: -0.0006

Data Index: 464494 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1277522 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0290. Min Act: -0.0006

Data Index: 49257 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0301. Min Act: -0.0006

Data Index: 378021 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0282. Min Act: -0.0006

Data Index: 48371 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1113168 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0297. Min Act: -0.0006

Data Index: 821118 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1176424 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0277. Min Act: -0.0005

Data Index: 368600 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0300. Min Act: -0.0006

Data Index: 762733 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1230901 (C4 (Web Text))

Max Activating Token Index: 668